website_discoverDiscovers website pages and advisory recommendations without importing them.
No durable receipt exists; timeout/loss leaves an unknown outcome and repetition is new work.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Website URL and excluded URL patterns for page recommendations. | |
| agent_id | Yes | Agent ID from agents_list or agent_create. |
| Name | Required | Description | Default |
|---|---|---|---|
| pages | Yes | ||
| total | Yes |
Changes observed during successful MCP inspections.
Input schema / $defs / WebsiteDiscoverRequest / properties / max_depthRemoved value: -{
- "default": 2,
- "maximum": 5,
- "minimum": 1,
- "title": "Max Depth",
- "type": "integer"
-}Input schema / properties / data / descriptionPrevious value: -"Website URL and excluded URL patterns for page recommendations; depth is a legacy input."New value: +"Website URL and excluded URL patterns for page recommendations."Input schema / properties / agent_id / descriptionAdded value: +"Agent ID from agents_list or agent_create."Input schema / properties / data / descriptionAdded value: +"Website URL and excluded URL patterns for page recommendations; depth is a legacy input."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds genuinely non-obvious operational context beyond the annotations: no durable receipt, timeout/loss yields an unknown outcome, and repetition counts as new work – consistent with idempotentHint=false. The gap is that readOnlyHint=false implies some persisted write (presumably a discovery/recommendation record), yet the description never says what state it creates.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences, no filler, with the core action front-loaded and the retry hazard immediately after. Every sentence carries information an agent would otherwise have to guess.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists so return shape needn't be described, and the annotations plus the retry-semantics sentence cover the safety profile well. The one missing piece is what the non-read-only call persists and whether a repeat pollutes anything besides being 'new work'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and both parameters (url, exclude_patterns) are documented in the schema, so the schema already does the heavy lifting. The description mentions discovering pages but adds nothing about URL format, matching scope for exclude patterns, or defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Names a specific verb and resource (discovers website pages and advisory recommendations) plus a scope qualifier ('without importing them') that implicitly separates it from the website_import sibling. It stops short of naming that sibling explicitly, so the differentiation requires a small inference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Without importing them' hints that this is a pre-import/preview step, but the description never states when to call this versus website_import, or what the agent should do with the recommendations afterward. Usage is implied rather than prescribed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.